AutomationBench-AA is Artificial Analysis' independent run of Zapier's AutomationBench private benchmark subset. It contains 657 business-workflow tasks across Finance, HR, Marketing, Operations, Sales, and Support in 40 simulated SaaS application environments. The headline metric counts objectives completed without any guardrail violation.
Browse the latest scores, model modes, release dates, and parameter sizes for AutomationBench-AA.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
No benchmark data available yet
